CN115267783A - Vehicle-mounted radar height target classification method, device, equipment and storage medium - Google Patents
Vehicle-mounted radar height target classification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115267783A CN115267783A CN202210727729.3A CN202210727729A CN115267783A CN 115267783 A CN115267783 A CN 115267783A CN 202210727729 A CN202210727729 A CN 202210727729A CN 115267783 A CN115267783 A CN 115267783A
- Authority
- CN
- China
- Prior art keywords
- target
- vehicle
- target objects
- height
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Abstract
The invention discloses a vehicle-mounted radar height target classification method, device, equipment and storage medium. The invention detects the speed of the vehicle, the relative radial speeds of a plurality of target objects and the azimuth angles of the target objects by controlling a millimeter wave radar of the vehicle; judging the motion states of a plurality of target objects according to the speed of the vehicle, the relative radial speeds of the plurality of target objects and the azimuth angles of the plurality of target objects; respectively acquiring pitch angle values of a plurality of moving target objects; acquiring an angle deviation value of the vehicle in the pitching direction according to the pitch angle value; correcting pitch angle values of a plurality of static target objects; controlling a millimeter wave radar of the vehicle to detect target distance values between a plurality of static target objects and the vehicle; acquiring target height values of a plurality of static target objects and the vehicle; and classifying the heights of the plurality of static target objects according to the target height values. The method can effectively improve the classification accuracy of the target object with the height dimension and improve the accuracy of obstacle avoidance of the automatic driving automobile.
Description
Technical Field
The invention relates to the technical field of automatic driving control, in particular to a vehicle-mounted radar height target classification method, device, equipment and storage medium.
Background
Millimeter wave radar is one of the key sensors in ADAS autonomous vehicles, and many ADAS functions such as AEB, ACC, FCW, etc. are accomplished with or only with millimeter wave radar. These functions are mainly decision-making decisions based on the targets ahead detected by the millimeter-wave radar. Among these targets, road signs and light poles hung in the air, well covers and speed bumps on the ground need to be filtered. Generally, as shown in fig. 1, the filtering of the targets is determined by calculating a height value H = r × sin Φ from a distance r and a pitch angle Φ of the targets measured by a radar.
Besides normal distance, doppler velocity and azimuth angle measurement, the radar in the 4D millimeter wave radar also needs pitch angle measurement capability, and the total number of dimensions is 4. When the radar is completely installed, there is usually a deviation of the installation angle. In the prior art, the method for mounting the deviation is to perform one-time off-line calibration on radar mounting before leaving a factory and correct the deviation of the mounting angle. The method can play a certain role, and when a vehicle runs normally, local undulation and jolt of a certain road surface are avoided, so that the pitch angle of a target measured by a radar with good calibration is also deviated, the calculated height of the target is not accurate, and the targets such as air and well covers are difficult to classify and filter. Therefore, the invention of a reliable vehicle-mounted radar height target classification method has become an urgent problem to be solved by technical personnel in the field.
Disclosure of Invention
The technical scheme includes that the motion states of a plurality of target objects on a road are judged according to the speed of a vehicle, the relative radial speeds of the plurality of target objects and the azimuth angles of the plurality of target objects; acquiring pitch angle values of a plurality of moving target objects, and acquiring an angle deviation value of the vehicle in the pitching direction according to the pitch angle values; correcting pitch angle values of a plurality of static target objects respectively according to the angle deviation value of the pitching direction of the vehicle; respectively acquiring target height values of a plurality of static target objects and the vehicle according to the target distance values; the heights of a plurality of static target objects are classified according to the target height values, so that the method can overcome the problems that the height measurement of the target objects is inaccurate due to the deviation of the installation angle of the millimeter wave radar, and the obstacle avoidance performance is poor due to the difficulty in classifying and filtering the targets such as the hollow well lid and the like,
in order to solve the technical problem, an embodiment of the present invention provides a vehicle-mounted radar height target classification method, where the method includes:
controlling a millimeter wave radar of the vehicle to detect the speed of the vehicle, the relative radial speeds of a plurality of target objects and the azimuth angles of the plurality of target objects;
judging the motion states of a plurality of target objects according to the speed of the vehicle, the relative radial speeds of the plurality of target objects and the azimuth angles of the plurality of target objects;
respectively acquiring pitch angle values of a plurality of moving target objects;
acquiring an angle deviation value of the pitching direction of the vehicle according to the pitch angle value;
respectively correcting the pitch angle values of the plurality of static target objects according to the angle deviation value;
a millimeter wave radar for controlling the vehicle detects target distance values between a plurality of static target objects and the vehicle;
respectively acquiring target height values of a plurality of static target objects and the vehicle according to the target distance values;
and classifying the heights of the plurality of static target objects according to the target height values.
Preferably, the determining the motion states of the plurality of target objects according to the speed of the vehicle, the relative radial speeds of the plurality of target objects, and the azimuth angles of the plurality of target objects includes:
if v isr+vccos theta =0, the target is determinedThe object is in an absolute static state;
wherein v isrAs relative radial velocity, vcTheta is the azimuth angle of the target object for the vehicle speed of the vehicle.
Preferably, the determining the motion states of the plurality of target objects according to the speed of the vehicle, the relative radial speeds of the plurality of target objects, and the azimuth angles of the plurality of target objects further includes:
if | vr+vcIf cos theta is larger than epsilon, determining that the target object is in a motion state;
wherein v isrAs relative radial velocity, vcTheta is the azimuth angle of the target object for the speed of the vehicle, and epsilon is a preset parameter value.
Preferably, the obtaining of the angle deviation value of the pitch direction of the vehicle according to the pitch angle value includes:
and acquiring the mean value or the median value of the pitch angle values of the moving target object as the angle deviation value of the vehicle in the pitch direction.
Preferably, the respectively correcting the pitch angle values of the plurality of stationary target objects according to the angle deviation values comprises:
respectively acquiring pitch angle values of a plurality of static target objects;
calculating a difference value between the pitch angle value and the angle deviation value;
and taking the difference value as a corrected pitch angle value.
Preferably, the formula for calculating the target height value among the target height values of the stationary target objects and the vehicle respectively obtained according to the target distance value is as follows:
wherein H is a target height value, r is a target distance value,
is the pitch angle value of the target object.
Preferably, said classifying the heights of a plurality of said stationary target objects according to said target height value comprises:
if the height target value is larger than a first preset height threshold value, the static target object is a first height type object;
and if the height target value is less than or equal to a second preset height threshold value, the static target object is a second height type object.
In order to solve the technical problem, an embodiment of the present invention provides a vehicle-mounted radar height target classification device, where the device includes:
the data detection module is used for controlling a millimeter wave radar of the vehicle to detect the speed of the vehicle, the relative radial speeds of a plurality of target objects and the azimuth angles of the plurality of target objects;
the judging module is used for judging the motion states of the target objects according to the speed of the vehicle, the relative radial speeds of the target objects and the azimuth angles of the target objects;
the pitch angle detection module is used for respectively acquiring pitch angle values of a plurality of moving target objects;
the deviation calculation module is used for acquiring an angle deviation value of the vehicle in the pitching direction according to the pitch angle value;
the correction module is used for respectively correcting the pitch angle values of the plurality of static target objects according to the angle deviation value;
the distance detection module is used for controlling a millimeter wave radar of the vehicle to detect target distance values between a plurality of static target objects and the vehicle;
the target height detection module is used for respectively acquiring target height values of a plurality of static target objects and the vehicle according to the target distance values;
and the classification module is used for classifying the heights of the plurality of static target objects according to the target height values.
In order to solve the technical problem, an embodiment of the present invention provides a vehicle-mounted radar height target classification method and device, including: at least one processor, at least one memory, and computer program instructions stored in the memory, which when executed by the processor, implement the method of the first aspect of the embodiments described above.
To solve the above technical problem, an embodiment of the present invention provides a storage medium having computer program instructions stored thereon, where the computer program instructions, when executed by a processor, implement the method according to the first aspect of the foregoing embodiments.
In summary, the embodiments of the present invention provide a method, an apparatus, a device, and a storage medium for classifying a vehicle radar height target. The invention detects the speed of the vehicle, the relative radial speeds of a plurality of target objects and the azimuth angles of the plurality of target objects by controlling the millimeter wave radar of the vehicle; judging the motion states of a plurality of target objects according to the speed of the vehicle, the relative radial speeds of the plurality of target objects and the azimuth angles of the plurality of target objects; respectively acquiring pitch angle values of a plurality of moving target objects; acquiring an angle deviation value of the pitching direction of the vehicle according to the pitch angle value; respectively correcting the pitch angle values of the plurality of static target objects according to the angle deviation value; controlling a millimeter wave radar of the vehicle to detect target distance values between a plurality of static target objects and the vehicle; respectively acquiring target height values of a plurality of static target objects and the vehicle according to the target distance values; and classifying the heights of the plurality of static target objects according to the target height values. Therefore, the angle deviation of the pitching direction of the vehicle is obtained through the pitching angle value of the moving target object, and the pitching angle of the static target object is corrected through the angle deviation of the pitching direction of the vehicle, so that the accuracy of height judgment of the static target object is improved, and the obstacle avoidance performance and the safety of the automatic driving vehicle are improved. Therefore, the method can effectively improve the classification accuracy of the target object with the height dimension and improve the accuracy of obstacle avoidance of the automatic driving automobile.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings may be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic diagram of a filtering principle of a background art of a vehicle-mounted radar height target classification method according to an embodiment of the present invention.
Fig. 2 is a scene schematic diagram of a vehicle radar height target classification method according to an embodiment of the present invention.
Fig. 3 is a schematic flow chart of a vehicle radar height target classification method according to an embodiment of the present invention.
Fig. 4 is a schematic flow chart illustrating a process of respectively correcting pitch angle values of a plurality of stationary target objects according to an angle deviation value in a method for classifying a height target of a vehicle-mounted radar according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of a vehicle-mounted radar height target classification device according to an embodiment of the invention.
Fig. 6 is a schematic structural diagram of a vehicle-mounted radar height target classification device according to an embodiment of the present invention.
Detailed Description
Features of various aspects and exemplary embodiments of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and the embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising 8230; \8230;" comprises 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
Referring to fig. 2, fig. 2 is a scene schematic diagram of a method for classifying high-altitude objects of a vehicle-mounted radar according to the present invention.
Referring to fig. 3, fig. 3 is a schematic flow chart of a method for classifying a high-altitude target of a vehicle-mounted radar according to the present invention.
The method comprises the following steps:
s1, a millimeter wave radar for controlling a vehicle detects the speed of the vehicle, relative radial speeds of a plurality of target objects and azimuth angles of the target objects;
in particular, when an autonomous vehicle is driving on a fixed road scene, it is necessary to perform driving assistance detection by a radar operating in a millimeter wave band for detection.
Specifically, the millimeter wave radar operates on the principle that a plurality of target objects can be simultaneously measured for distance, speed and azimuth by generating an electromagnetic wave of a specific modulation Frequency (FMCW) by a high frequency circuit, transmitting the electromagnetic wave through an antenna and receiving the electromagnetic wave reflected from the target. The speed measurement is that according to the Doppler effect, the movement speed of a target relative to a radar can be obtained by calculating the frequency change of the radar wave returned to a receiving antenna, and then the distance of the target object is obtained through the flight time; and azimuth measurement comprises horizontal angle and vertical angle, and the azimuth angle of the target is calculated by the phase difference of the radar waves reflected by the same target and received by the antenna array.
S2, judging the motion states of a plurality of target objects according to the speed of the vehicle, the relative radial speeds of the plurality of target objects and the azimuth angles of the plurality of target objects;
specifically, when an autonomous vehicle travels on a fixed road scene, there is at least one moving target object, such as a moving vehicle other than the vehicle, in addition to stationary target objects, such as various guideboards, signboards, manhole covers, speed bumps, height-limiting frames, and stationary vehicles, suspended in the air. In this embodiment, it is assumed that the moving vehicle is located right in front of the road surface of the traveling road of the vehicle, that is, around the pitch angle of 0 degrees, the moving vehicle is a moving target object that needs to be dynamically obstacle-avoided, and the high-altitude target object and the manhole cover on the ground are stationary target objects that need to be filtered.
In particular, since stationary target objects have no height information, it is completely impossible to decide whether these obstacles affect the passage of autonomous vehicles by means of 3D millimeter wave radars. For a static target object, the processing mode in the prior art is either directly ignored or the confidence coefficient is reduced, so that the camera does not recognize a white wagon compartment such as a toppled wagon compartment, and the millimeter wave radar recognizes the white wagon compartment, but the confidence coefficient is too low in decision, so that the vehicle does not trigger an automatic emergency braking function, and a traffic accident is caused.
S3, respectively obtaining pitch angle values of a plurality of moving target objects;
specifically, after determining whether the motion states of the plurality of target objects are moving or stationary, it is necessary to perform classification processing on moving objects and stationary objects. After the classification processing, the pitch angle values of a plurality of moving target objects measured by the millimeter wave radar are counted in the moving object class.
Specifically, in the application, the phase difference is calculated by receiving the same echo signal through a plurality of receiving antennas, so that the measurement of the azimuth angle is realized; and then, a plurality of single-chip transceivers are cascaded, the number of virtual channels is increased, and the measurement of the pitch angle is realized, which is not described herein again.
S4, acquiring an angle deviation value of the pitching direction of the vehicle according to the pitch angle value;
s5, respectively correcting the pitch angle values of the plurality of static target objects according to the angle deviation values;
specifically, the pitch angle value of the moving target object in front of the vehicle is taken as a reference in the application, so that the angle deviation value of the pitch direction of the vehicle is obtained; and then the pitch angle of the static target object is corrected through the angle deviation value of the pitch direction of the vehicle, so that the accuracy of the vehicle for measuring the pitch angle value of the static target object is improved, the static target objects such as various guideboards, signboards, well covers, speed reducing belts, height limiting frames and static vehicles suspended in the air on a road scene can be filtered and classified better, the confidence degree of the obstacle avoidance decision of the automatic driving vehicle is improved, and the safety performance of automatic driving is improved.
S6, controlling a millimeter wave radar of the vehicle to detect target distance values between a plurality of static target objects and the vehicle;
s7, respectively acquiring target height values of a plurality of static target objects and the vehicle according to the target distance values;
specifically, after the pitch angle values of the plurality of stationary target objects are obtained, the target distance values between the stationary target objects and the vehicle are obtained through the millimeter wave radar, and then the target height values of the plurality of stationary target objects and the vehicle are calculated according to the target distance values.
The above is only a specific implementation of obtaining the target height values of the plurality of stationary target objects and the host vehicle, which is described in the present application, and other implementations are also possible, and the present application is not particularly limited herein.
It should be noted that the number of the plurality of stationary target objects is statistically calculated by the target objects detected within the preset time period during the automatic driving of the vehicle, and the present application is not limited thereto.
And S8, classifying the heights of the plurality of static target objects according to the target height values.
Specifically, the heights of static target objects in a road driving scene are inconsistent, for example, various guideboards, signboards and the like suspended in the air are positioned at higher positions, and the subsequent automatic driving automobile for the high-altitude objects can be filtered without avoiding barriers; and well lid, deceleration strip, limit for height static vehicle and static target object such as are in lower position, need keep away the barrier to follow-up automatic driving car of this kind of static object, trigger automatic emergency braking function even in the decision-making, avoid the emergence of accident.
In conclusion, in the automatic driving process of the vehicle, the motion states of a plurality of target objects on a road are judged by acquiring the speed of the vehicle, the relative radial speeds of the plurality of target objects and the azimuth angles of the plurality of target objects; acquiring pitch angle values of a plurality of moving target objects, and acquiring an angle deviation value of the vehicle in the pitching direction according to the pitch angle values; correcting pitch angle values of a plurality of static target objects respectively according to the angle deviation value of the pitching direction of the vehicle; respectively acquiring target height values of a plurality of static target objects and the vehicle according to the target distance values; the heights of a plurality of static target objects are classified according to the target height values, so that the problem that due to the fact that the height of the target objects is inaccurate to measure due to installation angle deviation of the millimeter wave radar, targets such as hollow and well covers are difficult to classify and filter, and obstacle avoidance performance is poor can be solved. Therefore, the angle deviation of the pitching direction of the vehicle is obtained through the pitching angle value of the moving target object, and the pitching angle of the static target object is corrected through the angle deviation of the pitching direction of the vehicle, so that the accuracy of height judgment of the static target object is improved, and the obstacle avoidance performance and the safety of the automatic driving vehicle are improved.
On the basis of the above-described embodiment:
as a preferred embodiment, the determining the motion states of the plurality of target objects according to the speed of the vehicle, the relative radial velocities of the plurality of target objects, and the azimuth angles of the plurality of target objects includes:
if v isr+vcIf cos theta =0, the target object is judged to be in an absolute static state;
wherein v isrAs relative radial velocity, vcθ is the azimuth angle of the target object for the vehicle speed.
Specifically, the speed of the target object measured by the millimeter wave radar is a relative speed, and the absolute speed of the target object relative to the ground is obtained through the speed of the vehicle and the relative radial speed; and judging whether the target object is in a moving state or a static state according to whether the absolute speed is close to 0 or not.
As a preferred embodiment, the determining the motion states of the multiple target objects according to the speed of the vehicle, the relative radial velocities of the multiple target objects, and the azimuth angles of the multiple target objects further includes:
if | vr+vcIf cos theta is larger than epsilon, the target object is judged to be in a motion state;
wherein v isrAs relative radial velocity, vcThe speed of the vehicle is theta, theta is the azimuth angle of the target object, and epsilon is a preset parameter value.
Specifically, assume that in an actual scene, the host vehicle speed is vcThe azimuth angle of the target object relative to the vehicle is theta, and the parameter measured by the millimeter wave radar is relative radial velocity vrAzimuth angle θ and pitch angle
If the target object is stationary, the radial velocity of the stationary target object relative to the millimeter wave radar is
In practical situations, the height of the target object is usually limited, and when the target object is a little far away, the pitch angle is
Is smaller as shown in fig. 1, and thus
The above equation can be simplified to vr＝-vccos θ. Therefore, the requirement in the present application to determine that the target is absolutely stationary is vr+vccosθ＝0。
The above conditions are derived theoretically, provided that the variables have no error. In practice, however, engineering measurement errors necessarily exist, including the doppler velocity v of the radar measurementrAzimuth angle theta and vehicle speed v obtained from vehicle bodycAre all erroneous, so the requirement for the present application to determine that the target is absolutely stationary is | vr+vccos theta < epsilon. In the present application, epsilon is a preset fixed parameter value, for example, epsilon is set to 10% of the vehicle speed of the vehicle, and epsilon can be reasonably set, and is not particularly limited herein. It is thus possible to obtain,conversely, the sufficient condition for determining that the target is a moving target is | vr+vccosθ|＞ε。
As a preferred embodiment, the obtaining of the angle deviation value of the pitch direction of the host vehicle according to the pitch angle value comprises:
and acquiring the mean value or the median value of the pitch angle values of the moving target object as the angle deviation value of the pitching direction of the vehicle.
Specifically, after obtaining the pitch angle values of a plurality of moving target objects as described above
Then, the pitch angle values can be averaged or median-calculated to obtain a value
I.e. the angular deviation in one pitch direction of the vehicle. Where n represents the number of moving target objects.
It should be noted that, the number of the plurality of moving target objects is calculated statistically by the target objects detected within a preset time period during the automatic driving process of the vehicle, and the application is not limited herein.
Referring to fig. 4, fig. 4 is a schematic flow chart illustrating a process of respectively correcting pitch angle values of a plurality of stationary target objects according to an angle deviation value in a vehicle-mounted radar height target classification method provided by the present invention.
As a preferred embodiment, the correcting the pitch angle values of the plurality of stationary target objects, respectively, in accordance with the angle deviation values includes:
s51, respectively obtaining pitch angle values of a plurality of static target objects;
s52, calculating a difference value between the pitching angle value and the angle deviation value;
and S53, taking the difference value as the corrected pitch angle value.
In particular, in the present application, the pitch angle values of all stationary target objects are taken and corrected, i.e. the pitch angles thereof are corrected
Wherein
For the pitch angle value before the correction,
is the corrected pitch angle value. Therefore, the method and the device can improve the accuracy of the vehicle in measuring the pitch angle value of the static target object, and improve the confidence of the obstacle avoidance decision of the automatic driving vehicle and the safety performance of the automatic driving.
As a preferred embodiment, the calculation formula for obtaining the target height value of the target height values of the plurality of stationary target objects and the host vehicle according to the target distance values is as follows:
wherein H is a target height value, r is a target distance value,
is the pitch angle value of the target object.
As a preferred embodiment, classifying the heights of the plurality of stationary target objects according to the target height value includes:
if the height target value is greater than a first preset height threshold value, the static target object is a first height type object;
and if the height target value is less than or equal to a second preset height threshold value, the static target object is a second height type object.
Specifically, the first preset height value of the present application is set to 3m, that is, when the target height value is greater than 3m, the stationary target object is determined to be various guideboards, signboards, stationary cars, etc. suspended in mid-air; the second preset height value is set to 0.2m, namely when the target height value is less than or equal to 0.2m, the static target object is judged as a well lid, a speed bump and the like. It is understood that, in the present embodiment, the specific values of the first preset height value and the second preset height value are set according to actual situations, and are not limited specifically herein.
Referring to fig. 5, fig. 5 is a block diagram of a vehicle-mounted radar height target classification device provided in the present invention, where the system includes:
the data detection module 1 is used for controlling a millimeter wave radar of the vehicle to detect the speed of the vehicle, the relative radial speeds of a plurality of target objects and the azimuth angles of the plurality of target objects;
the judging module 2 is used for judging the motion states of a plurality of target objects according to the speed of the vehicle, the relative radial speeds of the plurality of target objects and the azimuth angles of the plurality of target objects;
the pitch angle detection module 3 is used for respectively acquiring pitch angle values of a plurality of moving target objects;
the deviation calculation module 4 is used for acquiring an angle deviation value of the vehicle in the pitching direction according to the pitch angle value;
the correcting module 5 is used for respectively correcting the pitch angle values of the plurality of static target objects according to the angle deviation value;
the distance detection module 6 is used for controlling the millimeter wave radar of the vehicle to detect target distance values between a plurality of static target objects and the vehicle;
the target height detection module 7 is used for respectively obtaining target height values of a plurality of static target objects and the vehicle according to the target distance values;
and the classification module 8 is used for classifying the heights of the plurality of static target objects according to the target height values.
In addition, the vehicle-mounted radar height target classification method of the embodiment of the invention described in conjunction with fig. 1 can be realized by vehicle-mounted radar height target classification equipment. Fig. 6 shows a hardware structure schematic diagram of a vehicle-mounted radar height target classification method device provided by an embodiment of the invention.
The in-vehicle radar height target classification device may comprise a processor 401 and a memory 402 storing computer program instructions.
Specifically, the processor 401 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured as one or more Integrated circuits implementing embodiments of the present invention.
The processor 401 reads and executes the computer program instructions stored in the memory 402 to implement any one of the vehicle radar height target classification methods in the above embodiments.
In one example, an in-vehicle radar height target classification method apparatus may also include a communication interface 403 and a bus 410. As shown in fig. 6, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 to complete communication therebetween.
The communication interface 403 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present invention.
In addition, in combination with the vehicle-mounted radar height target classification method in the foregoing embodiment, an embodiment of the present invention may be implemented by providing a computer-readable storage medium. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any one of the vehicle radar height target classification methods in the above embodiments.
It should also be noted that the exemplary embodiments noted in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present invention.
Claims (10)
1. A vehicle radar height target classification method is characterized by comprising the following steps:
controlling a millimeter wave radar of the vehicle to detect the speed of the vehicle, the relative radial speeds of a plurality of target objects and the azimuth angles of the plurality of target objects;
judging the motion states of a plurality of target objects according to the speed of the vehicle, the relative radial speeds of the plurality of target objects and the azimuth angles of the plurality of target objects;
respectively acquiring pitch angle values of a plurality of moving target objects;
acquiring an angle deviation value of the pitching direction of the vehicle according to the pitching angle value;
respectively correcting the pitch angle values of the plurality of static target objects according to the angle deviation values;
controlling a millimeter wave radar of the vehicle to detect target distance values between a plurality of static target objects and the vehicle;
respectively acquiring target height values of a plurality of static target objects and the vehicle according to the target distance values;
and classifying the heights of the plurality of static target objects according to the target height values.
2. The method as claimed in claim 1, wherein the determining the motion states of the plurality of target objects according to the speed of the vehicle, the relative radial velocities of the plurality of target objects, and the azimuth angles of the plurality of target objects comprises:
if v isr+vcIf cos theta =0, determining that the target object is in an absolute static state;
wherein v isrAs relative radial velocity, vcTheta is the azimuth angle of the target object for the vehicle speed of the vehicle.
3. The method as claimed in claim 1, wherein the determining the motion states of the plurality of target objects according to the speed of the vehicle, the relative radial velocities of the plurality of target objects, and the azimuth angles of the plurality of target objects further comprises:
if | vr+vcIf cos theta is larger than epsilon, determining that the target object is in a motion state;
wherein v isrIn a relatively radial directionVelocity, vcThe speed of the vehicle is theta, theta is the azimuth angle of the target object, and epsilon is a preset parameter value.
4. The method as claimed in claim 1, wherein the obtaining the angle deviation value of the pitch direction of the vehicle according to the pitch angle value comprises:
and acquiring the mean value or the median value of the pitch angle values of the moving target object as the angle deviation value of the vehicle in the pitch direction.
5. The method as claimed in claim 4, wherein the step of respectively modifying the pitch angle values of the plurality of stationary target objects according to the angle deviation value comprises:
respectively acquiring pitch angle values of a plurality of static target objects;
calculating a difference between the pitch angle value and the angle deviation value;
and taking the difference value as a corrected pitching angle value.
6. The method as claimed in claim 5, wherein the formula for obtaining the target height value from the target height values of the stationary target objects and the host vehicle according to the target distance value is:
wherein H is a target height value, r is a target distance value,
is the pitch angle value of the target object.
7. The vehicle-mounted radar height target classification method according to claim 1, wherein the classifying the heights of the plurality of static target objects according to the target height value comprises:
if the height target value is larger than a first preset height threshold value, the static target object is a first height type object;
and if the height target value is less than or equal to a second preset height threshold value, the static target object is a second height type object.
8. An on-vehicle radar height target classification device, characterized in that the device comprises:
the data detection module is used for controlling a millimeter wave radar of the vehicle to detect the speed of the vehicle, the relative radial speeds of a plurality of target objects and the azimuth angles of the plurality of target objects;
the judging module is used for judging the motion states of the target objects according to the speed of the vehicle, the relative radial speeds of the target objects and the azimuth angles of the target objects;
the pitch angle detection module is used for respectively acquiring pitch angle values of a plurality of moving target objects;
the deviation calculation module is used for acquiring an angle deviation value of the vehicle in the pitching direction according to the pitch angle value;
the correction module is used for respectively correcting the pitch angle values of the plurality of static target objects according to the angle deviation value;
the distance detection module is used for controlling a millimeter wave radar of the vehicle to detect target distance values between a plurality of static target objects and the vehicle;
the target height detection module is used for respectively acquiring target height values of a plurality of static target objects and the vehicle according to the target distance values;
and the classification module is used for classifying the heights of the plurality of static target objects according to the target height values.
9. An on-vehicle radar height target classification device, characterized by comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, which when executed by the processor, implement the method of any one of claims 1-7.
10. A storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210727729.3A CN115267783A (en) | 2022-06-23 | 2022-06-23 | Vehicle-mounted radar height target classification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210727729.3A CN115267783A (en) | 2022-06-23 | 2022-06-23 | Vehicle-mounted radar height target classification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115267783A true CN115267783A (en) | 2022-11-01 |
Family
ID=83761929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210727729.3A Pending CN115267783A (en) | 2022-06-23 | 2022-06-23 | Vehicle-mounted radar height target classification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115267783A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115656962A (en) * | 2022-12-26 | 2023-01-31 | 南京楚航科技有限公司 | Method for identifying height-limited object based on millimeter wave radar |
-
2022
- 2022-06-23 CN CN202210727729.3A patent/CN115267783A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115656962A (en) * | 2022-12-26 | 2023-01-31 | 南京楚航科技有限公司 | Method for identifying height-limited object based on millimeter wave radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110785798B (en) | Traffic environment adaptive threshold | |
| US6567737B2 (en) | Vehicle control method and vehicle warning method | |
| CN107728618B (en) | Obstacle avoidance method of unmanned ship | |
| JP3087606B2 (en) | Apparatus and method for measuring distance between vehicles | |
| JP2900737B2 (en) | Inter-vehicle distance detection device | |
| US6675094B2 (en) | Path prediction system and method | |
| EP2023158A2 (en) | Automotive forward looking sensor with identification of traversable stationary obstacles in the driving path | |
| US20120101704A1 (en) | Method for operating at least one sensor of a vehicle and vehicle having at least one sensor | |
| US10585188B2 (en) | Broadside detection system and techniques for use in a vehicular radar | |
| US9669838B2 (en) | Method and system for information use | |
| TWI509275B (en) | Alarm system and method for vehicle | |
| JP2009133761A (en) | Radar system | |
| WO2018143237A1 (en) | Information processing device, server device, information processing system, information processing method, and program | |
| JP2020197506A (en) | Object detector for vehicles | |
| CN115267783A (en) | Vehicle-mounted radar height target classification method, device, equipment and storage medium | |
| US11307292B2 (en) | ODM information reliability determination system and method and vehicle using the same | |
| JP2001216596A (en) | Road detector and automatic vehicle | |
| KR20210101877A (en) | Apparatus and method for blind-spot collision warning of vehicle | |
| CN219512394U (en) | Radar system for detecting angle of full plane | |
| US20230166736A1 (en) | Method and apparatus for tracking road facility based on vehicle motion characteristics | |
| JP7324059B2 (en) | Vehicle object detection device | |
| US20230251369A1 (en) | Radar control apparatus and method | |
| US20230001923A1 (en) | Vehicular automatic emergency braking system with cross-path threat determination | |
| WO2022244316A1 (en) | Radar device | |
| JP2000111644A (en) | Vehicle detecting device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |